Artificial wetland water treatment method and device based on photovoltaic array layout optimization

Abstract

The application provides a kind of artificial wetland water treatment method and device based on photovoltaic array layout optimization, for improving the power generation efficiency of artificial wetland water treatment system, artificial wetland water treatment system is used to support artificial wetland water treatment, method includes: obtaining the initial layout parameter of photovoltaic array;Initial layout parameter includes: photovoltaic board coordinates and photovoltaic board inclination;Initial layout parameter is carried out genetic algorithm optimization processing, and target layout parameter after optimization is obtained;Photovoltaic array is adjusted based on target layout parameter, and target photovoltaic array is obtained;Power generation is carried out through target photovoltaic array, and electric energy is obtained;Electric energy is input to hybrid energy storage unit for power supply and / or energy storage, after power supply and / or energy storage, energy distribution is carried out through intelligent energy distribution unit, and real-time monitoring is carried out through remote monitoring and maintenance unit after energy distribution.

Description

Technical Field

[0001] This invention relates to the field of constructed wetland water treatment technology, and in particular to a constructed wetland water treatment method and apparatus based on photovoltaic array layout optimization. Background Technology

[0002] Constructed wetlands are ecological engineering systems built to simulate natural wetlands. They utilize plants, microorganisms, and substrates to purify water, and simultaneously improve water quality, restore the ecosystem, and regulate water resources. The management of constructed wetlands has a significant impact on improving water purification efficiency, optimizing resource utilization, and ensuring flood and drought resistance capabilities.

[0003] However, the energy management of constructed wetlands still faces the problems of high energy consumption and high cost. For example, equipment such as aeration and water pumps require continuous power supply, and their energy consumption accounts for 40%-60% of the operating cost. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide an artificial wetland water treatment method and apparatus based on photovoltaic array layout optimization, so as to improve power generation efficiency and realize energy storage, thereby solving the problems of high energy consumption and high cost.

[0005] In a first aspect, embodiments of the present invention provide a method for constructed wetland water treatment based on photovoltaic array layout optimization, used to improve the power generation efficiency of constructed wetland water treatment systems. The constructed wetland water treatment system supports constructed wetland water treatment and includes: a renewable energy acquisition unit, a hybrid energy storage unit, an intelligent energy distribution unit, and a remote monitoring and maintenance unit. The method includes: acquiring initial layout parameters of the photovoltaic array; the initial layout parameters include: photovoltaic panel coordinates and photovoltaic panel tilt angle; performing genetic algorithm optimization on the initial layout parameters to obtain optimized target layout parameters; adjusting the photovoltaic array based on the target layout parameters to obtain the target photovoltaic array; generating electricity through the target photovoltaic array; inputting the electricity into the hybrid energy storage unit for power supply and / or energy storage; distributing the energy through the intelligent energy distribution unit after power supply and / or energy storage; and monitoring the energy distribution in real time through the remote monitoring and maintenance unit.

[0006] In a preferred embodiment of the present invention, the above-mentioned genetic algorithm optimization of the initial layout parameters to obtain the optimized target layout parameters includes: encoding the initial layout parameters to generate a chromosome population containing photovoltaic panel coordinates and photovoltaic panel tilt angles; evaluating the fitness of the chromosome population to obtain fitness values; and performing simulated binary crossover and Gaussian mutation operations on the chromosome population based on the fitness values ​​to generate the target layout parameters.

[0007] In a preferred embodiment of the present invention, the above-mentioned fitness assessment of the chromosome population to obtain a fitness value includes: determining the fitness value using the following fitness function: The fitness function combines the average daily power generation with the shadow overlap area, where APG represents the average daily power generation and SOA represents the shadow overlap area. .

[0008] In a preferred embodiment of the present invention, the above-described simulated binary crossover operation on the chromosome population includes: selecting parent gene values ​​from the chromosome population; and generating offspring gene values ​​based on the simulated binary crossover algorithm using the following formula: Where x1 and x2 represent the parent gene values, and β represents the offspring gene value, and is used to control the degree of difference between offspring and parent genes; β is expressed by the following formula: Where r represents a random number, This represents the distribution parameter.

[0009] In a preferred embodiment of the present invention, the above-mentioned Gaussian mutation operation includes: adding Gaussian perturbation to genes in a chromosome population; and generating mutated genes using the following formula: ;in, This represents the mutated gene, where x represents the original gene. It indicates that it follows a standard normal distribution. random numbers, This indicates the magnitude of the disturbance.

[0010] In a preferred embodiment of the present invention, the above-mentioned adjustment of the photovoltaic array based on the target layout parameters to obtain the target photovoltaic array includes: adjusting the photovoltaic panel coordinates and photovoltaic panel tilt angle based on the target layout parameters; driving the photovoltaic panel with a stepper motor to track the solar azimuth angle and altitude angle in real time to control the error.

[0011] In a preferred embodiment of the present invention, the renewable energy acquisition unit includes: a dual-axis tracking photovoltaic array and a vertical-axis wind turbine, used to dynamically optimize the layout of the photovoltaic array through a genetic algorithm to improve power generation efficiency; the hybrid energy storage unit includes: a lithium battery pack and a supercapacitor pack, used to achieve dynamic energy distribution through a bidirectional DC / DC converter, with the lithium battery pack providing continuous power supply and the supercapacitor pack responding to instantaneous high power demands; the intelligent energy distribution unit is used to dynamically optimize energy distribution strategies by collecting real-time data on irradiance, wind speed, energy storage state of charge, and load demand based on a deep reinforcement learning algorithm; and the remote monitoring and maintenance unit is used to monitor the system status in real-time through a sensor network, performing anomaly warnings, predictive maintenance, and remote strategy updates.

[0012] Secondly, embodiments of the present invention also provide an artificial wetland water treatment device based on photovoltaic array layout optimization, used to improve the power generation efficiency of the artificial wetland water treatment system. The artificial wetland water treatment system supports artificial wetland water treatment and includes: a renewable energy acquisition unit, a hybrid energy storage unit, an intelligent energy distribution unit, and a remote monitoring and maintenance unit. The device includes: an initial layout parameter acquisition module for acquiring the initial layout parameters of the photovoltaic array; the initial layout parameters include: photovoltaic panel coordinates and photovoltaic panel tilt angle; an initial layout parameter optimization module for performing genetic algorithm optimization on the initial layout parameters to obtain optimized target layout parameters; a photovoltaic array adjustment module for adjusting the photovoltaic array based on the target layout parameters to obtain the target photovoltaic array; a target photovoltaic array power generation module for generating electricity through the target photovoltaic array; and an energy input module for inputting the energy into the hybrid energy storage unit for power supply and / or energy storage, and then distributing the energy through the intelligent energy distribution unit after power supply and / or energy storage, and finally monitoring the energy in real time through the remote monitoring and maintenance unit.

[0013] Thirdly, embodiments of the present invention also provide an electronic device, including a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the artificial wetland water treatment method based on photovoltaic array layout optimization described in the first aspect.

[0014] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer-executable instructions. When the computer-executable instructions are invoked and executed by a processor, the computer-executable instructions cause the processor to implement the artificial wetland water treatment method based on photovoltaic array layout optimization described in the first aspect.

[0015] The embodiments of the present invention bring the following beneficial effects:

[0016] This invention provides a method and apparatus for constructed wetland water treatment based on photovoltaic array layout optimization. The method involves obtaining initial layout parameters of the photovoltaic array, optimizing these parameters using a genetic algorithm to obtain optimized target layout parameters, adjusting the photovoltaic array based on these parameters, and generating electricity through the target photovoltaic array. This electricity is then input into a hybrid energy storage unit for power supply and / or energy storage. After power supply and / or energy storage, the energy is distributed through an intelligent energy distribution unit, and then monitored in real-time by a remote monitoring and maintenance unit. This approach improves power generation efficiency, achieves energy storage, and solves the problems of high energy consumption and high cost.

[0017] Other features and advantages of this disclosure will be set forth in the following description, or some features and advantages may be inferred from the description or determined without doubt, or may be learned by practicing the techniques described above.

[0018] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0019] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0020] Figure 1 A flowchart illustrating an artificial wetland water treatment method based on photovoltaic array layout optimization, provided for an embodiment of the present invention;

[0021] Figure 2 A flowchart of another artificial wetland water treatment method based on photovoltaic array layout optimization provided in an embodiment of the present invention;

[0022] Figure 3 A flowchart illustrating the operation of a renewable energy harvesting unit provided in an embodiment of the present invention;

[0023] Figure 4 A flowchart illustrating the operation of a hybrid energy storage unit according to an embodiment of the present invention;

[0024] Figure 5 A flowchart of a smart energy distribution unit provided in an embodiment of the present invention;

[0025] Figure 6 A flowchart of a remote monitoring and maintenance unit provided in an embodiment of the present invention;

[0026] Figure 7 A schematic diagram of a constructed wetland water treatment device based on photovoltaic array layout optimization provided in an embodiment of the present invention;

[0027] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] Constructed wetlands are ecological engineering systems built to simulate natural wetlands. They utilize plants, microorganisms, and substrates to purify water, combining water quality improvement, ecological restoration, and water resource regulation. Constructed wetland management has a significant impact on improving water purification efficiency, optimizing resource utilization, and ensuring flood and drought resistance. The core of constructed wetland management lies in dynamic water allocation to ensure ecological balance, synergistic effects between water purification and flood and drought control, improve resource efficiency, and respond to sudden environmental changes.

[0030] However, the energy management of constructed wetlands still faces the problems of high energy consumption and high cost. For example, equipment such as aeration and water pumps require continuous power supply, and their energy consumption accounts for 40%-60% of the operating cost.

[0031] Based on this, the present invention provides an artificial wetland water treatment method and apparatus based on photovoltaic array layout optimization. This method involves obtaining the initial layout parameters of the photovoltaic array, optimizing these parameters using a genetic algorithm to obtain optimized target layout parameters, adjusting the photovoltaic array based on these parameters to obtain the target photovoltaic array, generating electricity through the target photovoltaic array, and inputting this electricity into a hybrid energy storage unit for power supply and / or energy storage. After power supply and / or energy storage, the energy is distributed through an intelligent energy distribution unit, and then monitored in real time through a remote monitoring and maintenance unit. This approach improves power generation efficiency, achieves energy storage, and solves the problems of high energy consumption and high cost.

[0032] To facilitate understanding of this embodiment, a detailed description of an artificial wetland water treatment method based on photovoltaic array layout optimization disclosed in this embodiment of the invention will be provided first.

[0033] Example 1

[0034] This invention provides a method for constructed wetland water treatment based on photovoltaic array layout optimization, which is used to improve the power generation efficiency of the constructed wetland water treatment system. The constructed wetland water treatment system is used to support constructed wetland water treatment and includes: a renewable energy acquisition unit, a hybrid energy storage unit, an intelligent energy distribution unit, and a remote monitoring and maintenance unit. Figure 1 This is a flowchart illustrating an artificial wetland water treatment method based on photovoltaic array layout optimization, provided as an embodiment of the present invention. Figure 1As shown, the constructed wetland water treatment method based on photovoltaic array layout optimization may include the following steps:

[0035] Step S101: Obtain the initial layout parameters of the photovoltaic array.

[0036] The initial layout parameters include: photovoltaic panel coordinates and photovoltaic panel tilt angle.

[0037] Step S102: Perform genetic algorithm optimization on the initial layout parameters to obtain the optimized target layout parameters.

[0038] Specifically, the initial layout parameters are optimized using a genetic algorithm to obtain the optimized target layout parameters. This can include: encoding the initial layout parameters to generate a chromosome population containing the coordinates and tilt angles of the photovoltaic panels; evaluating the fitness of the chromosome population to obtain fitness values; and performing simulated binary crossover and Gaussian mutation operations on the chromosome population based on the fitness values ​​to generate the target layout parameters.

[0039] The fitness assessment of a chromosome population to obtain a fitness value can include determining the fitness value using the following fitness function: The fitness function combines the average daily power generation with the shadow overlap area, where APG represents the average daily power generation and SOA represents the shadow overlap area. .

[0040] The simulated binary crossover operation on the chromosome population may include: selecting parent gene values ​​from the chromosome population; and generating offspring gene values ​​based on the simulated binary crossover algorithm using the following formula: Where x1 and x2 represent the parent gene values, and β represents the offspring gene value, and is used to control the degree of difference between offspring and parent genes; β is expressed by the following formula: Where r represents a random number, This represents the distribution parameter.

[0041] The Gaussian mutation operation can include: adding Gaussian perturbations to genes in a chromosome population; and generating the mutated genes using the following formula: ;in, This represents the mutated gene, where x represents the original gene. It indicates that it follows a standard normal distribution. random numbers, This indicates the magnitude of the disturbance.

[0042] Step S103: Adjust the photovoltaic array based on the target layout parameters to obtain the target photovoltaic array.

[0043] Specifically, adjusting the photovoltaic array based on the target layout parameters to obtain the target photovoltaic array may include: adjusting the photovoltaic panel coordinates and tilt angle based on the target layout parameters; and driving the photovoltaic panels with a stepper motor to track the solar azimuth and elevation angles in real time to control errors.

[0044] Step S104: Power is generated through the target photovoltaic array to obtain electrical energy.

[0045] Step S105: Electrical energy is input to the hybrid energy storage unit for power supply and / or energy storage. After power supply and / or energy storage, energy is distributed through the intelligent energy distribution unit. After energy distribution, it is monitored in real time through the remote monitoring and maintenance unit.

[0046] The renewable energy harvesting unit includes a dual-axis tracking photovoltaic array and a vertical-axis wind turbine, which are used to dynamically optimize the layout of the photovoltaic array through a genetic algorithm to improve power generation efficiency.

[0047] The hybrid energy storage unit includes a lithium battery pack and a supercapacitor pack, which are used to achieve dynamic energy distribution through a bidirectional DC / DC converter. The lithium battery pack is used for continuous power supply, and the supercapacitor pack is used to respond to instantaneous high power demands.

[0048] The intelligent energy distribution unit is used to collect data on light intensity, wind speed, energy storage state of charge, and load demand in real time based on deep reinforcement learning algorithms, and to dynamically optimize energy distribution strategies.

[0049] The remote monitoring and maintenance unit is used to monitor the system status in real time through a sensor network, and to perform anomaly warnings, predictive maintenance, and remote policy updates.

[0050] The constructed wetland water treatment method based on photovoltaic array layout optimization provided in this invention involves obtaining the initial layout parameters of the photovoltaic array, optimizing these parameters using a genetic algorithm to obtain optimized target layout parameters, adjusting the photovoltaic array based on these target parameters to obtain the target photovoltaic array, generating electricity through the target photovoltaic array, and inputting the electricity into a hybrid energy storage unit for power supply and / or energy storage. After power supply and / or energy storage, the energy is distributed through an intelligent energy distribution unit, and then monitored in real time through a remote monitoring and maintenance unit. This method improves power generation efficiency, achieves energy storage, and solves the problems of high energy consumption and high cost.

[0051] Example 2

[0052] This invention also provides another artificial wetland water treatment method based on photovoltaic array layout optimization; this method is implemented based on the method in the above embodiments.

[0053] Figure 2A flowchart of another artificial wetland water treatment method based on photovoltaic array layout optimization provided in this embodiment of the invention is shown below. Figure 2 As shown, the constructed wetland water treatment method based on photovoltaic array layout optimization may include the following steps:

[0054] Step S201: Optimize the layout of the photovoltaic array through the renewable energy acquisition unit to obtain the target photovoltaic array, and generate electricity through the target photovoltaic array.

[0055] For ease of understanding, Figure 3 This is a flowchart illustrating the operation of a renewable energy harvesting unit provided in an embodiment of the present invention.

[0056] like Figure 3 As shown, the dual-axis photovoltaic array and vertical-axis wind turbine are started, tracking the solar angle and collecting wind energy respectively. Each sensor monitors data such as light intensity, temperature, wind speed, and power, and transmits this data to the control center. The control center uses a genetic algorithm to optimize the photovoltaic array layout, outputting an optimized solution to improve power generation efficiency, ultimately completing the energy collection and layout optimization work.

[0057] The core of the renewable energy harvesting unit lies in achieving efficient energy capture through multi-source complementarity and intelligent optimization. This unit consists of a dual-axis tracking photovoltaic array, a small vertical-axis wind turbine, and a genetic algorithm-based layout optimization system. The dual-axis photovoltaic array is driven by a stepper motor, tracking the solar azimuth (horizontal) and altitude (vertical) angles in real time to ensure the photovoltaic panels are always perpendicular to the incident sunlight. The vertical-axis wind turbine has a rated power of 1kW and a starting wind speed as low as 2m / s, adapting to multi-wind-direction environments. It can compensate for photovoltaic power generation gaps during cloudy, rainy, or nighttime conditions, ensuring continuous energy supply.

[0058] Optimizing the layout of photovoltaic arrays is key to improving efficiency. Since an improper layout can lead to shading, a genetic algorithm is used to dynamically optimize the installation angle and spacing. The algorithm encodes the photovoltaic panel coordinates (X, Y) and tilt angle θ into chromosomes, which can initialize 100 layout schemes. The optimal solution is selected through a fitness function. The fitness function, the simulated binary crossover algorithm, and the addition of Gaussian perturbation have been described in detail in step S102 above and will not be repeated here.

[0059] After 50 iterations, the algorithm can be considered to output the optimal layout, effectively solving the shading problem. The optimized photovoltaic array and wind power generation work synergistically to significantly reduce the operating cost of the constructed wetland system. SBX adjusts the offspring diversity through parameters and combines local perturbations from Gaussian mutation to ensure that the algorithm has both global exploration and local optimization capabilities. In practical applications, the synergy between the simulated binary crossover algorithm and Gaussian mutation effectively avoids local optima, ensuring that the layout schemes are evenly distributed in the solution space.

[0060] In practical applications, by integrating dual-axis tracking photovoltaics and vertical-axis wind power generation, and dynamically optimizing the photovoltaic array layout through genetic algorithms, the shading problem is solved, thereby improving power generation efficiency.

[0061] Step S202: Dynamic energy distribution is achieved through hybrid energy storage units.

[0062] The hybrid energy storage unit is a core component of the constructed wetland energy management system. It aims to resolve the conflict between instantaneous high power demand and continuous stable power supply through the synergistic design of lithium batteries and supercapacitors. The lithium battery pack, serving as the main energy storage unit, has a capacity of 20kWh and is primarily used for continuous power supply during prolonged low-load scenarios such as nighttime water pump operation. The supercapacitor pack, as the auxiliary energy storage unit, leverages its rapid charge-discharge characteristics to prioritize responses to instantaneous high power demands (such as the peak current during aerator startup). Both units achieve dynamic energy distribution through a bidirectional DC / DC converter, and combined with intelligent control strategies, significantly improve the system's reliability and energy efficiency.

[0063] For ease of understanding, Figure 4 This is a flowchart illustrating the operation of a hybrid energy storage unit according to an embodiment of the present invention.

[0064] like Figure 4 As shown, when the hybrid energy storage unit is working, it first determines the power demand of the load. If the demand is greater than 5kW, the supercapacitor bank is prioritized for discharge; otherwise, the lithium battery bank provides power. The bidirectional DC / DC converter regulates the discharge rate and provides charge / discharge protection. A loss balancing strategy periodically switches the charge / discharge path. When there is excess photovoltaic or wind power, the supercapacitor is charged first; when the energy storage's state of charge is >90%, the system switches to charging the lithium battery bank, thus achieving efficient energy storage and stable power supply.

[0065] As a core power electronic device enabling bidirectional energy flow, the bidirectional DC / DC converter plays a crucial role in energy storage systems, electric vehicles, and renewable energy fields. It ensures efficient system operation by dynamically adjusting the charge and discharge rates to balance efficiency and stability.

[0066] The core of the control strategy lies in adjusting the duty cycle, frequency, or phase shift. Basic methods include voltage-mode control, such as adjusting the duty cycle through output voltage deviation, which offers strong stability but a slower response; and current-mode control, such as directly regulating inductor current, suitable for scenarios requiring rapid response, such as the instantaneous discharge of supercapacitors. In advanced strategies, closed-loop control works in conjunction with the outer loop; for example, during charging, the outer loop limits the upper limit of the battery voltage, while the inner loop constrains the peak current.

[0067] This application's embodiment employs a dual active bridge (DAB) topology, achieving efficient energy transfer through a high-frequency isolation transformer. Specifically, the power is expressed using the following formula: ;in, and Indicates the voltage across both sides. Indicates the phase shift angle. Indicates the switching frequency. This indicates leakage inductance; phase-shift control dynamically adjusts the direction and magnitude of power transmission by adjusting the phase shift angle, ensuring flexible scheduling of hybrid energy storage.

[0068] Key influencing factors include electrical parameters and environmental conditions: the input / output voltage difference determines the power that can be transmitted, but it is necessary to avoid exceeding the device's withstand voltage; the inductance value affects the current ripple, for example, a small inductor has a fast response but a large ripple; the capacitance determines the voltage stability when the load changes abruptly; although high-frequency switching reduces the size of components, it increases switching losses; rising temperature will limit the maximum current, and heat dissipation design is needed to maintain power capability.

[0069] For example, the selection of inductor parameters requires a trade-off between dynamic response and ripple, which can be expressed by the following formula: ;in, Indicates the duty cycle; Indicates the switching frequency.

[0070] In practical applications, in scenarios where aerators frequently start and stop, supercapacitors respond quickly to instantaneous loads, avoiding capacity decay caused by frequent charging and discharging of lithium batteries; while lithium batteries provide stable power at night, reducing dependence on the power grid. Tests show that this unit improves system energy utilization and reduces operating costs. Compared to traditional single energy storage solutions, this invention, through multi-source collaboration and dynamic optimization, achieves highly reliable and low-loss energy management, providing technical support for the promotion of constructed wetland systems in remote areas.

[0071] In practical applications, by using lithium batteries and supercapacitors for complementary energy storage, combined with a bidirectional DC / DC converter to dynamically allocate energy, the supercapacitors prioritize responding to instantaneous high power demands, while the lithium batteries ensure continuous power supply, thus improving energy utilization.

[0072] Step S203: The intelligent energy distribution unit collects data on light intensity, wind speed, energy storage charge status and load demand in real time, and dynamically optimizes the energy distribution strategy.

[0073] For ease of understanding, Figure 5 This is a flowchart illustrating the operation of an intelligent energy distribution unit provided in an embodiment of the present invention.

[0074] like Figure 5As shown, the intelligent energy allocation unit first constructs a simulation environment based on the OpenAIGym framework, integrating data to determine the state and action space, and processes it using an Actor-Critic architecture and LSTM layers. After designing the reward function, it performs offline training and online fine-tuning, and then deploys the trained deep reinforcement learning model to edge computing devices. Sensors collect data to input into the model to generate instructions, which are executed by the control center, and the execution results are fed back to the cloud, realizing dynamic energy allocation.

[0075] In this embodiment, the bidirectional DC / DC converter is combined with a hybrid energy storage unit and a deep reinforcement learning algorithm to significantly improve energy utilization. Deep reinforcement learning (DRL) combines deep neural networks with reinforcement learning, dynamically optimizing charging and discharging strategies by learning environmental conditions in real time, such as photovoltaic output and load demand. Its objective function can be expressed by the following formula: ;in, , This represents the weighting coefficient, used to balance charging gains and losses.

[0076] The core objective of deep reinforcement learning algorithms is to dynamically allocate energy from renewable energy sources, such as solar and wind power, and energy storage systems, prioritizing power supply to core equipment like aerators and pumps while minimizing energy consumption and equipment wear. To achieve this, the algorithm first constructs a simulation environment based on the OpenAI Gym framework, integrating dynamic data, including real-time light intensity and wind speed (for solar and wind power output), the state of charge (SOC) of energy storage systems (lithium batteries and supercapacitors), and equipment load demands (divided into primary and secondary loads). The input features of the state space include solar power generation, wind power generation, energy storage SOC, real-time load power demands, and equipment health status. The action space involves energy allocation ratios, such as the dynamic allocation ratio of solar, wind, and energy storage, and the equipment start-up and shutdown sequence. An Actor-Critic architecture is employed, where the Actor network outputs the action probability distribution, and the Critic network evaluates state values ​​to guide the Actor in optimizing the strategy. The input layer uses LSTM layers to capture temporal features, such as the periodicity of weather changes and load fluctuation trends.

[0077] The design of the reward function is key to guiding the agent to learn the optimal strategy. Positive rewards include +10 points for every 1% increase in energy utilization, while negative penalties include deducting 5 points for every 10% decrease in storage SOC to prevent over-discharge, and deducting 20 points for each power outage to ensure the operation of core equipment.

[0078] The reward function is expressed by the following formula: ;in, This represents the change in energy efficiency. Indicates the rate of decline of the state of charge of energy storage. This indicates the number of times the device has been powered off.

[0079] The algorithm training is divided into two stages: offline training and online fine-tuning. In the offline training stage, historical data can be used to construct a training set, and the data can be standardized. The Actor network adopts a 3-layer fully connected structure (input layer - LSTM - output layer) with ReLU activation function; the Critic network contains 2 fully connected layers, outputting the state value Q-value.

[0080] For example, during training, the agent interacts with the environment 1000 times, each time containing 24 hours of simulated data (with a time step of 1 minute). After each interaction, the experience (state, action, reward, next state) is stored in the replay pool, and the network is updated in batches using random sampling. During the online fine-tuning phase, the latest weather forecasts and device load curves are synchronized to the edge computing device at intervals, the Critic network weights are frozen, and only the Actor network is fine-tuned. At the same time, a transfer learning strategy is used to retain the general features from the historical training.

[0081] Finally, the trained deep reinforcement learning model is deployed to local edge computing devices in the wetland, such as NVIDIA Jetson. Sensors collect real-time data on illumination, state of charge, and load, which are then input into the deep reinforcement learning model to generate action commands, such as energy allocation ratios and device start / stop. The control center executes these commands and adjusts operations such as photovoltaic panel angles and energy storage charging / discharging. The execution results are fed back to the cloud platform for the next round of fine-tuning.

[0082] In practical applications, energy allocation strategies are optimized in real time based on deep reinforcement learning algorithms to prioritize power supply to core equipment. Time-series data is processed using LSTM and combined with a dynamic reward mechanism to reduce operating costs.

[0083] Step S204: Monitor the system status in real time through the remote monitoring and maintenance unit, and perform anomaly warnings, predictive maintenance, and remote policy updates.

[0084] For ease of understanding, Figure 6 This is a flowchart illustrating the operation of a remote monitoring and maintenance unit provided in an embodiment of the present invention.

[0085] like Figure 6 As shown, the remote monitoring and maintenance unit first collects energy and equipment status data via a sensor network, transmits it to the edge gateway for preprocessing and caching via LoRaWAN, and then uploads it to the cloud platform via 4G / 5G. The cloud stores and analyzes the data, displaying it through a visual interface. If an anomaly is detected, it triggers early warnings and emergency responses; it can also perform predictive maintenance and remote policy updates to ensure stable system operation.

[0086] The remote monitoring and maintenance unit is built on the artificial wetland energy management system in the patent. Its core function is to use cloud platform and Internet of Things (IoT) technology to monitor the energy status and equipment health of the artificial wetland system in real time, and to support remote maintenance and strategy optimization.

[0087] Specifically, this unit can monitor energy status, such as photovoltaic power generation, energy storage status of charge, and equipment energy consumption, as well as equipment health in real time. By dynamically displaying the system's operating status, it allows maintenance personnel to clearly understand the system's working condition. Simultaneously, the unit also features anomaly warning and emergency response functions, capable of promptly triggering alarms and activating protection mechanisms to address potential faults. Furthermore, predictive maintenance can predict equipment lifespan and failure risks based on data analysis, enabling proactive maintenance. The remote policy update function allows for the distribution of new parameters or algorithm models via the cloud, achieving continuous system optimization.

[0088] The system architecture of this unit consists of a data acquisition layer, an edge computing layer, and a cloud platform layer. The data acquisition layer uses a sensor network to monitor energy and equipment status. Energy monitoring includes current / voltage sensors and temperature sensors, while equipment status monitoring encompasses vibration sensors and flow meters. These sensors can collect data such as photovoltaic and wind power output, energy storage unit temperature rise, aerator operating status, and water pump workload. For communication protocols, the unit uses LoRaWAN and MQTT. LoRaWAN is a low-power wide-area network protocol that supports long-distance, low-speed data transmission, suitable for remote areas; MQTT is a lightweight messaging protocol used for efficient communication between the device and the cloud.

[0089] The local edge gateway in the edge computing layer is mainly responsible for data preprocessing, such as filtering and normalization; and local caching, such as temporarily storing data when the network is interrupted. Its hardware usually uses embedded devices such as NVIDIA Jetson Nano to run lightweight AI models to achieve preliminary diagnosis of device faults.

[0090] The cloud platform layer is responsible for data storage and analysis. Time-series databases, such as InfluxDB, are used to store time-series data such as photovoltaic power generation and state of charge curves, while big data analytics engines, such as Apache Spark, process terabytes of historical data and generate energy consumption reports. In addition, the visualization interface includes dashboards and historical curve comparison functions. The dashboards can display energy status, equipment health, and environmental parameters in real time, while the historical curve comparison supports daily / monthly / yearly analysis of power generation efficiency and load fluctuation trends.

[0091] In terms of key technology implementation, this unit possesses anomaly early warning and emergency response functions. Its early warning rule base covers low thresholds for energy storage state of charge (SBC), such as SBC < 20%, and equipment overload, such as pump current exceeding rated value by 10%. These scenarios trigger SMS / email alarms, start backup diesel generators, automatically reduce load, or switch to redundant equipment, respectively. The multi-level alarm mechanism is divided into level one alarms (e.g., local audible and visual alarms), level two alarms (e.g., cloud-based push notifications to maintenance personnel), and level three alarms (e.g., initiating emergency shutdown). For predictive maintenance, the unit uses a random forest model to predict lithium battery life. Input features include historical charge / discharge cycles, average depth of discharge, ambient temperature, and capacity decay curves. When the predicted capacity drops to, for example, 80%, a replacement alarm is triggered, and a maintenance plan is recommended. Equipment fault diagnosis is based on vibration spectrum analysis. By comparing normal and abnormal vibration signals of the aerator, problems such as bearing wear or blade imbalance are identified. Remote policy updates are achieved through OTA (Over-The-Air) technology, enabling firmware upgrades and policy adjustments. Examples include cloud-based distribution of new control algorithms, updates to deep reinforcement learning model parameters, or dynamic modifications to energy allocation rules, such as adjusting supercapacitor discharge thresholds. For security, the unit employs data encryption and digital signature verification to prevent malicious tampering.

[0092] For example, in practical applications, the data acquisition process of this unit involves the sensor collecting data every 5 minutes, transmitting it to the edge gateway via LoRaWAN, and then uploading the compressed data to the cloud via a 4G / 5G network. When analyzing the data, if the cloud platform detects a continuous decline in the lithium battery's SOC and a sudden increase in load, it will trigger a deep reinforcement learning algorithm to reallocate energy (prioritizing wind power supplementation). The predictive maintenance unit will prompt the maintenance team to schedule a replacement when it detects that the lithium battery pack capacity has dropped to 82%. For remote intervention, engineers can temporarily increase the supercapacitor discharge threshold through the cloud platform to cope with sudden high load demands.

[0093] In practical applications, real-time monitoring is achieved by utilizing sensor networks and an "edge-cloud" architecture, integrating random forest lifetime prediction and OTA policy updates, supporting anomaly warnings and remote maintenance, and improving system reliability.

[0094] In practical applications, in order to realize the functions of the above units, it is necessary to deploy corresponding sensors to improve the "sensing-response" system.

[0095] Specifically, in the photovoltaic array of the renewable energy harvesting unit, a light intensity sensor is placed on the surface of the photovoltaic panel or on the central support of the array to monitor the actual received light intensity. A temperature sensor is attached to the back of the photovoltaic panel to monitor the operating temperature and prevent overheating that could lead to efficiency degradation. A current / voltage sensor is installed in the combiner box or at the input of the inverter to collect the photovoltaic output power in real time.

[0096] Specifically, in the wind turbine of the renewable energy harvesting unit, anemometers and wind vanes are installed at the top of the tower or in an open area around it, for example, at a height of ≥10 meters, to avoid turbulence interference. Vibration sensors are fixed to the generator bearing housing to monitor mechanical vibrations to prevent blade imbalance or bearing wear. Current / voltage sensors are located at the generator output to monitor real-time power generation.

[0097] Specifically, in the lithium battery pack of the hybrid energy storage unit, voltage / current sensors are installed at the series terminals of each individual battery cell or module to monitor the state of charge and discharge. Temperature sensors are evenly distributed inside the battery pack and on the surface of the casing to focus on monitoring hot spots. The state of charge estimation unit is integrated into the battery management system (BMS) for calibration via coulomb counting and open-circuit voltage.

[0098] Specifically, in the supercapacitor bank of the hybrid energy storage unit, voltage sensors are placed across each capacitor module to monitor instantaneous charge and discharge voltage fluctuations. Temperature sensors are attached to the capacitor heat sink to prevent overheating from causing capacity degradation.

[0099] Specifically, the load device can include primary load and secondary load. The primary load can be an aerator or a water pump, and the secondary load can be a sensor or a communication module.

[0100] In a primary load configuration, a current / voltage sensor is mounted at the power input to monitor energy consumption in real time. A vibration sensor is fixed to the motor housing to detect abnormal vibrations, such as accelerations > 5 m / s². 2 An alarm is triggered when the water flow is detected. A flow sensor (for the water pump only) is located in the outlet pipe to monitor the actual water flow.

[0101] In the secondary load, the power consumption monitoring module is integrated into the device's power supply circuit to record standby and operating power consumption. Status indicator sensors detect the online status of the communication module, such as detecting LoRaWAN signal strength.

[0102] Specifically, regarding environmental parameter monitoring, temperature and humidity sensors are placed near the photovoltaic array, inside the energy storage unit cabinet, and around the wetland treatment pond. This data is used to correct the photovoltaic efficiency model and heat dissipation strategy. Light sensors, independent of the photovoltaic panels, are installed in unobstructed areas, such as the top of a monitoring pole, to provide independent light data and verify the actual light-gathering efficiency of the photovoltaic panels. Rainfall sensors are placed in open areas around the wetland, avoiding obstruction by foliage, to monitor rainfall and optimize energy storage scheduling strategies during cloudy and rainy days.

[0103] The constructed wetland water treatment method based on photovoltaic array layout optimization provided in this invention involves the following steps: After system startup, the dual-axis tracking photovoltaic array and vertical-axis wind turbine of the renewable energy acquisition unit collect energy and transmit it to the hybrid energy storage unit for storage. The intelligent energy distribution unit analyzes environmental data using a deep reinforcement learning algorithm to determine energy distribution and equipment operation instructions, which are then executed by the control center. The remote monitoring and maintenance module collects, processes, and analyzes data in real time, enabling anomaly warnings, predictive maintenance, and remote strategy updates. Related measures are fed back to adjust the system, ensuring stable system operation.

[0104] Example 3

[0105] Corresponding to the above method embodiments, this invention provides an artificial wetland water treatment device based on photovoltaic array layout optimization, which is used to improve the power generation efficiency of the artificial wetland water treatment system. The artificial wetland water treatment system is used to support artificial wetland water treatment and includes: a renewable energy acquisition unit, a hybrid energy storage unit, an intelligent energy distribution unit, and a remote monitoring and maintenance unit. Figure 7 A schematic diagram of an artificial wetland water treatment device based on photovoltaic array layout optimization is provided in an embodiment of the present invention, as shown below. Figure 7 As shown, the constructed wetland water treatment device based on photovoltaic array layout optimization may include the following modules:

[0106] The initial layout parameter acquisition module 301 is used to acquire the initial layout parameters of the photovoltaic array; the initial layout parameters include: photovoltaic panel coordinates and photovoltaic panel tilt angle.

[0107] The initial layout parameter optimization module 302 is used to perform genetic algorithm optimization on the initial layout parameters to obtain the optimized target layout parameters.

[0108] The photovoltaic array adjustment module 303 is used to adjust the photovoltaic array based on the target layout parameters to obtain the target photovoltaic array.

[0109] The target photovoltaic array power generation module 304 is used to generate electricity through the target photovoltaic array to obtain electrical energy.

[0110] The power input module 305 is used to input power into the hybrid energy storage unit for power supply and / or energy storage. After power supply and / or energy storage, the power is distributed through the intelligent energy distribution unit, and the energy is monitored in real time through the remote monitoring and maintenance unit.

[0111] The constructed wetland water treatment device based on photovoltaic array layout optimization provided in this invention can obtain the initial layout parameters of the photovoltaic array, optimize these parameters using a genetic algorithm to obtain optimized target layout parameters, adjust the photovoltaic array based on these target layout parameters to obtain the target photovoltaic array, generate electricity through the target photovoltaic array, input the electricity into a hybrid energy storage unit for power supply and / or energy storage, distribute the energy through an intelligent energy distribution unit, and monitor the energy distribution in real time through a remote monitoring and maintenance unit. This method improves power generation efficiency, achieves energy storage, and solves the problems of high energy consumption and high cost.

[0112] In some embodiments, the initial layout parameter optimization module is further configured to encode the initial layout parameters to generate a chromosome population containing photovoltaic panel coordinates and photovoltaic panel tilt angle; to evaluate the fitness of the chromosome population to obtain fitness values; and to perform simulated binary crossover and Gaussian mutation operations on the chromosome population based on the fitness values ​​to generate target layout parameters.

[0113] In some embodiments, the initial layout parameter optimization module is further configured to determine the fitness value using the following fitness function: The fitness function combines the average daily power generation with the shadow overlap area, where APG represents the average daily power generation and SOA represents the shadow overlap area. .

[0114] In some embodiments, the initial layout parameter optimization module is further used to select parent gene values ​​from the chromosome population; and to generate offspring gene values ​​based on the simulated binary crossover algorithm using the following formula: Where x1 and x2 represent the parent gene values, and β represents the offspring gene value, and is used to control the degree of difference between offspring and parent genes; β is expressed by the following formula: Where r represents a random number, This represents the distribution parameter.

[0115] In some embodiments, the initial layout parameter optimization module is further used to add Gaussian perturbations to the genes in the chromosome population; and to generate the mutated genes using the following formula: ;in, This represents the mutated gene, where x represents the original gene. It indicates that it follows a standard normal distribution. random numbers, This indicates the magnitude of the disturbance.

[0116] In some embodiments, the photovoltaic array adjustment module is also used to adjust the photovoltaic panel coordinates and photovoltaic panel tilt angle based on the target layout parameters; and to drive the photovoltaic panel with a stepper motor to track the solar azimuth and elevation angle in real time to control errors.

[0117] In some embodiments, the renewable energy harvesting unit includes: a dual-axis tracking photovoltaic array and a vertical-axis wind turbine, used to dynamically optimize the layout of the photovoltaic array through a genetic algorithm to improve power generation efficiency; the hybrid energy storage unit includes: a lithium battery pack and a supercapacitor pack, used to achieve dynamic energy distribution through a bidirectional DC / DC converter, with the lithium battery pack providing continuous power and the supercapacitor pack responding to instantaneous high power demands; the intelligent energy distribution unit is used to dynamically optimize energy distribution strategies by collecting real-time data on irradiance, wind speed, energy storage state of charge, and load demand based on a deep reinforcement learning algorithm; and the remote monitoring and maintenance unit is used to monitor the system status in real-time through a sensor network, performing anomaly warnings, predictive maintenance, and remote strategy updates.

[0118] The device provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0119] Example 4

[0120] This invention also provides an electronic device for running the above-described constructed wetland water treatment method based on photovoltaic array layout optimization; see also Figure 8 The diagram shows the structure of an electronic device, which includes a memory 400 and a processor 401. The memory 400 stores one or more computer instructions, which are executed by the processor 401 to implement the above-mentioned artificial wetland water treatment method based on photovoltaic array layout optimization.

[0121] Furthermore, Figure 8 The electronic device shown also includes a bus 402 and a communication interface 403. The processor 401, the communication interface 403 and the memory 400 are connected via the bus 402.

[0122] The memory 400 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 403 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc. The bus 402 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 8 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0123] Processor 401 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 401 or by instructions in software form. Processor 401 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a readily available storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 400, and processor 401 reads information from memory 400 and, in conjunction with its hardware, completes the steps of the method described in the foregoing embodiments.

[0124] This invention also provides a computer-readable storage medium storing computer-executable instructions. When these computer-executable instructions are called and executed by a processor, they cause the processor to implement the aforementioned artificial wetland water treatment method based on photovoltaic array layout optimization. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0125] The computer program product for the artificial wetland water treatment method based on photovoltaic array layout optimization provided in this embodiment of the invention includes a computer-readable storage medium storing non-volatile program code executable by a processor. The instructions included in the program code can be used to execute the methods described in the preceding method embodiments. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0126] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0127] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interface; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0128] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0129] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0130] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0131] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for treating artificial wetlands based on photovoltaic array layout optimization, characterized in that, This method is used to improve the power generation efficiency of an constructed wetland water treatment system. The constructed wetland water treatment system supports constructed wetland water treatment and includes: a renewable energy acquisition unit, a hybrid energy storage unit, a smart energy distribution unit, and a remote monitoring and maintenance unit. The method includes: Obtain the initial layout parameters of the photovoltaic array; the initial layout parameters include: photovoltaic panel coordinates and photovoltaic panel tilt angle; The initial layout parameters are optimized using a genetic algorithm to obtain the optimized target layout parameters; The photovoltaic array is adjusted based on the target layout parameters to obtain the target photovoltaic array; Electricity is generated through the target photovoltaic array; The electrical energy is input to the hybrid energy storage unit for power supply and / or energy storage. After power supply and / or energy storage, the energy is distributed through the intelligent energy distribution unit. After energy distribution, the energy is monitored in real time through the remote monitoring and maintenance unit. The genetic algorithm optimization process includes: encoding the photovoltaic panel coordinates (X, Y) and tilt angle θ into chromosomes, initializing 100 layout schemes, and outputting the optimal layout after 50 iterations to solve the shading problem; The renewable energy harvesting unit includes a dual-axis tracking photovoltaic array and a vertical-axis wind turbine, which is used to dynamically optimize the layout of the photovoltaic array through a genetic algorithm to improve power generation efficiency. The hybrid energy storage unit includes a lithium battery pack and a supercapacitor pack, which are used to achieve dynamic energy distribution through a bidirectional DC / DC converter. The lithium battery pack is used for continuous power supply, and the supercapacitor pack is used to respond to instantaneous high power demand. The intelligent energy distribution unit is used to collect data on light intensity, wind speed, energy storage state of charge and load demand in real time based on deep reinforcement learning algorithms, and dynamically optimize energy distribution strategies. The remote monitoring and maintenance unit is used to monitor the system status in real time through a sensor network, perform anomaly warnings, predictive maintenance, and remote strategy updates. The reward function of the deep reinforcement learning algorithm includes at least: a positive reward for improved energy utilization, a negative penalty for decreased energy storage state of charge, and a negative penalty for power outages. The reward function is expressed by the following formula: ;in, Represents the reward function, This represents the change in energy efficiency. Indicates the rate of decline of the state of charge of energy storage. Indicates the number of times the device has been powered off; The predictive maintenance includes using a random forest model to predict the lifespan of lithium batteries based on historical charge-discharge cycles, average depth of discharge, ambient temperature, and capacity decay curves, and triggering a replacement alarm when the predicted capacity is lower than a preset power threshold.

2. The method according to claim 1, characterized in that, The step of performing genetic algorithm optimization on the initial layout parameters to obtain the optimized target layout parameters includes: The initial layout parameters are encoded to generate a chromosome population containing the coordinates and tilt angle of the photovoltaic panel; Fitness values ​​are obtained by assessing the fitness of a chromosome population; Based on the fitness value, simulated binary crossover and Gaussian mutation operations are performed on the chromosome population to generate the target layout parameters.

3. The method according to claim 2, characterized in that, The fitness value obtained by evaluating the fitness of the chromosome population includes: The fitness value is determined using the following fitness function: ; The fitness function combines the average daily power generation and the shadow overlap area, where APG represents the average daily power generation and SOA represents the shadow overlap area. .

4. The method according to claim 3, characterized in that, The simulated binary crossover operation on the chromosome population includes: Select parental gene values ​​from the said chromosome population; The offspring gene values ​​are generated based on the simulated binary crossover algorithm using the following formula: Where x1 and x2 represent the parent gene values, and This represents the offspring gene value, with β used to control the degree of difference between offspring and parent genes. β is expressed by the following formula: Where r represents a random number, This represents the distribution parameter.

5. The method according to claim 4, characterized in that, The Gaussian mutation operation includes: Add Gaussian perturbations to the genes in the aforementioned chromosome population; The mutated gene is generated using the following formula: ;in, This represents the mutated gene, where x represents the original gene. It indicates that it follows a standard normal distribution. random numbers, This indicates the magnitude of the disturbance.

6. The method according to claim 1, characterized in that, The step of adjusting the photovoltaic array based on the target layout parameters to obtain the target photovoltaic array includes: Adjust the coordinates and tilt angle of the photovoltaic panel based on the target layout parameters; The photovoltaic panel is driven by a stepper motor to track the solar azimuth and elevation angles in real time to control errors.

7. An artificial wetland water treatment device based on photovoltaic array layout optimization, characterized in that, The device is used to implement the constructed wetland water treatment method based on photovoltaic array layout optimization as described in any one of claims 1 to 6, for improving the power generation efficiency of the constructed wetland water treatment system, wherein the constructed wetland water treatment system supports constructed wetland water treatment, and the constructed wetland water treatment system includes: a renewable energy acquisition unit, a hybrid energy storage unit, an intelligent energy distribution unit, and a remote monitoring and maintenance unit, and the device includes: An initial layout parameter acquisition module is used to acquire the initial layout parameters of the photovoltaic array; the initial layout parameters include: photovoltaic panel coordinates and photovoltaic panel tilt angle; The initial layout parameter optimization module is used to perform genetic algorithm optimization on the initial layout parameters to obtain the optimized target layout parameters; A photovoltaic array adjustment module is used to adjust the photovoltaic array based on the target layout parameters to obtain the target photovoltaic array; The target photovoltaic array power generation module is used to generate electricity through the target photovoltaic array to obtain electrical energy; The power input module is used to input the power into the hybrid energy storage unit for power supply and / or energy storage. After power supply and / or energy storage, the power is distributed through the intelligent energy distribution unit, and the energy is monitored in real time through the remote monitoring and maintenance unit.

8. An electronic device, characterized in that, The device includes a processor and a memory, the memory storing computer-executable instructions that can be executed by the processor, the processor executing the computer-executable instructions to implement the artificial wetland water treatment method based on photovoltaic array layout optimization as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the artificial wetland water treatment method based on photovoltaic array layout optimization as described in any one of claims 1 to 6.

Images